Seasonal (monthly) Trends
library(readxl)
#read in daily weather data
weather <- read_xlsx("SUD Weather Station.xlsx")
## New names:
## • `` -> `...22`
#read in hourly weather data
hourly<-read_xlsx("SUD Weather Station.xlsx", sheet=2)
## Warning: Expecting date in A2766 / R2766C1: got '11 RECORDS MISSING FROM LOGGER'
## Warning: Expecting date in A3629 / R3629C1: got 'MISSING DATA'
## Warning: Expecting date in A4604 / R4604C1: got 'MISSING DATA'
## Warning: Expecting date in A5375 / R5375C1: got 'MISSING DATA'
## Warning: Expecting date in A6071 / R6071C1: got 'MISSING DATA'
#read in recorded rain data
rain<-read_xlsx("SUD Weather Station.xlsx", sheet = 3)
#simple plot for weather (average daily temp)
###bat activity month column 1-12, rain has month column
#rename column names in weather df
colnames(weather)
## [1] "Date Values Reflect" "Timestamp*"
## [3] "Panel Temp???" "Air temp Avg (C)"
## [5] "Air Temp Max (C)" "Time Air Temp Max"
## [7] "Air Temp Min" "Time Air Temp Min"
## [9] "Wind Speed Avg (low) (m/S)" "Wind Speed Max (low) (m/s)"
## [11] "Time wind speed max (low)" "Wind Speed Min (low) (m/s)"
## [13] "Time wind speed min (low)" "Wind Speed Avg (high) (m/S)"
## [15] "Wind Speed Max (high) (m/s)" "Time wind speed max (high)"
## [17] "Wind Speed Min (high) (m/s)" "Time wind speed min (high)"
## [19] "VWC AVG (m³/m³)" "Solar Total (MJ/m²)"
## [21] "ET Total (mm)" "...22"
weather <- weather %>%
dplyr::rename("Date" = "Timestamp*",
AvgTemp='Air temp Avg (C)',
Highest_Temp_Time='Time Air Temp Max',
MaxTemp='Air Temp Max (C)',
MinTemp='Air Temp Min',
MaxWind='Wind Speed Max (low) (m/s)',
AvgWind='Wind Speed Avg (high) (m/S)',
MinWind='Wind Speed Min (low) (m/s)')
#variable with date, wind cols and temp cols
#Daily_Weather<-DailyTemp %>%
#
hourly<-hourly %>%
mutate(Date= date(Timestamp))
#create 'rainfall' variable to get the avg. rainfall per recorded day
rainfall<-hourly %>%
group_by(Date) %>%
summarise(total_rainfall = sum(`Rain (mm)`))
#rainfall monthly for each year
hourly<-hourly %>%
mutate(Month= month(Timestamp))
#rainfall yearly
hourly<-hourly %>%
mutate(Year= year(Timestamp))
yearly_rainfall <- hourly %>%
drop_na( Year ) %>%
group_by(Year) %>%
summarise(yearly_rainfall= sum(`Rain (mm)`))
View(yearly_rainfall)
#ignoring 2017 and NA bc it wasn't enough data
monthly_rainfall<-hourly %>%
group_by(Month,Year) %>%
summarise(total_monthly_rainfall = sum(`Rain (mm)`)) %>%
filter(Year>2017)
## `summarise()` has grouped output by 'Month'. You can override using the
## `.groups` argument.
View(monthly_rainfall)
df <- bats %>%
mutate(Month= month(DATE)) %>%
mutate(Year= year(DATE)) %>%
group_by(Month, Year, AUTO.ID) %>%
tally() %>%
ungroup()
df <- left_join(df, monthly_rainfall, by=c('Month', 'Year'))
###
df %>%
filter(Year>2017)
## # A tibble: 576 × 5
## Month Year AUTO.ID n total_monthly_rainfall
## <dbl> <dbl> <chr> <int> <dbl>
## 1 1 2019 EPTFUS 2 75.8
## 2 1 2019 LASCIN 11 75.8
## 3 1 2019 LASNOC 6 75.8
## 4 1 2020 EPTFUS 20 26.5
## 5 1 2020 LASBOR 113 26.5
## 6 1 2020 LASCIN 4231 26.5
## 7 1 2020 LASNOC 96 26.5
## 8 1 2020 MYOGRI 19 26.5
## 9 1 2020 MYOLEI 3 26.5
## 10 1 2020 MYOLUC 9 26.5
## # … with 566 more rows
#plot monthly rainfall
ggplot(data = monthly_rainfall, aes(x=Month, y=total_monthly_rainfall, fill=Year))+
geom_area()+
labs(title='Monthly Rainfall by Year', caption = 'Sewanee Bat Study. DataLab 2022', y='Total Rainfall (mm)')+
facet_wrap(~Year)+
theme( legend.position = "none" ) +
scale_x_continuous(breaks = 1:12)
library(ggplot2)
#create Year and Month variable from Date column
df <- df %>%
mutate( Date = ymd(paste0( Year, "-", Month, "-1") ) )
view(df)
#filter out 2017 and 2022; not enough data
df<-df%>%
filter(Year>2017, Year<2022)
#convert temp.from Celsius to Fahrenheit#
#Max temp
Fahrenheit<-weather %>%
mutate(MaxTemp_f = MaxTemp*(9/5)+32)
#Min temp
Fahrenheit<-Fahrenheit %>%
mutate(MinTemp_f = MinTemp*(9/5)+32)
#Average temp
Fahrenheit<-Fahrenheit %>%
mutate(AvgTemp_f = AvgTemp*(9/5)+32)
#merge df and fahrenheit
#first need to create a month and year column in Fahrenheit data set
Fahrenheit<-Fahrenheit %>%
mutate(Month= month(Date)) %>%
mutate(Year= year(Date))
#Get the mean of min, max, and average temp to plot better.
df.2<-Fahrenheit %>%
group_by(Month, Year) %>%
summarise(AvgTemp_f = mean(`AvgTemp_f`),
MaxTemp_f = mean(`MaxTemp_f`),
MinTemp_f = mean(`MinTemp_f`))
## `summarise()` has grouped output by 'Month'. You can override using the
## `.groups` argument.
drop_na(df.2)
## # A tibble: 45 × 5
## # Groups: Month [12]
## Month Year AvgTemp_f MaxTemp_f MinTemp_f
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 2019 39.2 47.6 31.6
## 2 1 2020 42.6 50.9 35.1
## 3 1 2021 39.3 48.7 31.9
## 4 2 2019 48.1 57.8 39.3
## 5 2 2020 41.0 50.6 32.5
## 6 2 2021 39.3 48.3 31.2
## 7 3 2018 42.7 52.9 33.4
## 8 3 2019 47.4 56.9 37.8
## 9 3 2020 54.5 63.4 46.9
## 10 3 2021 54.1 63.1 45.8
## # … with 35 more rows
df.2<-df.2%>%
filter(Year>2017, Year<2022)
#plot max, min, avg temp
ggplot(data = df.2, aes(x=Month, ymin=MinTemp_f, ymax=MaxTemp_f, y=AvgTemp_f))+
geom_ribbon(fill = "lightpink")+
geom_line(color="red")+
labs(title = 'Temperature ', subtitle = 'Maximum, Minimum, and Average', caption = 'Sewanee Bat Study. DataLab 2022', y='Temperature (°F)')+
facet_wrap(~Year)+
scale_x_continuous(breaks = 1:12)
#wind monthly for each year
windy<-weather %>%
mutate(Month= month(Date)) %>%
mutate(Year= year(Date))
#mean of wind ?intensity?
df.3<-windy %>%
group_by(Month, Year) %>%
summarise(AvgWind = mean(`AvgWind`),
MaxWind = mean(`MaxWind`),
MinWind = mean(`MinWind`))
## `summarise()` has grouped output by 'Month'. You can override using the
## `.groups` argument.
drop_na(df.3)
## # A tibble: 45 × 5
## # Groups: Month [12]
## Month Year AvgWind MaxWind MinWind
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 2019 3.11 10.9 0.0306
## 2 1 2020 3.27 11.6 0.0773
## 3 1 2021 2.20 9.15 0
## 4 2 2019 3.34 10.7 0
## 5 2 2020 3.14 11.0 0
## 6 2 2021 2.41 9.75 0
## 7 3 2018 2.99 9.95 0
## 8 3 2019 2.95 10.3 0
## 9 3 2020 2.82 10.2 0
## 10 3 2021 3.38 11.5 0
## # … with 35 more rows
df.3<-df.3%>%
filter(Year>2017, Year<2022)
#plot wind ?intensity?
ggplot(data = df.3, aes(x=Month, ymin=MinWind, ymax=MaxWind, y=AvgWind))+
geom_ribbon(fill = "gray")+
geom_line(color="darkgray")+
labs(title='Monthly Wind Intensity', subtitle = 'By year', caption= 'Sewanee Bat Study. DataLab 2022',y='Total Wind Speed (m/s)')+
facet_wrap(~Year)+
theme( legend.position = "none" ) +
scale_x_continuous(breaks = 1:12)
#overall temp. trends across the years on one graph
#just the average
#mean of temp
yearly_rainfall<-yearly_rainfall%>%
filter(Year>2017, Year<2022)
ggplot(data=df.2, aes(x=Month, y=AvgTemp_f, group=Year, color=Year))+
geom_line()+
labs(title = 'Overall Averages for Temperature ', caption = 'Sewanee Bat Study. DataLab 2022', y='Temperature (°F)')+
scale_x_continuous(breaks = 1:12)
#plot yearly rainfall
ggplot(data = yearly_rainfall, aes(x=Year, y=yearly_rainfall, fill=Year))+
geom_col()+
theme( legend.position = "none" ) +
labs(title='Overall Rainfall', caption = 'Sewanee Bat Study. DataLab 2022', y='Total Rainfall (mm)')
source('dataRead.R')
##
## Attaching package: 'scales'
## The following object is masked from 'package:purrr':
##
## discard
## The following object is masked from 'package:readr':
##
## col_factor
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(readxl)
batspecies <- read_excel("BatSpecies.xlsx")
bats <- bats %>%
rename( siteID = sensor) %>%
select(-LATITUDE,-LONGITUDE)
# sensor data read -----
source('dataRead-sensorDates.R')
# join bats and sensor site data -----
bats <- left_join(bats,sensorDates, by=c('siteID','DATE'))
No.ID = c("Noise", "NoId", "NoID")
bats<-left_join(bats,batspecies, by="AUTO.ID")
###
bats.time <- bats %>%
filter(! AUTO.ID %in% No.ID, year < 2022) %>%
group_by(year) %>%
mutate(nsensors = length(unique(siteID)))
# another code segment to utilize another group_by, this time so i can see the relative frequency of the species per year
bats.time <- bats.time %>%
group_by(monthN, year, AUTO.ID) %>%
summarize(count = n(),
rel_freq = count/nsensors)
## `summarise()` has grouped output by 'monthN', 'year', 'AUTO.ID'. You can
## override using the `.groups` argument.
bats.time <- unique(bats.time)
#this is just the plot, its copied almost exactly below so we could put it inside of an object to be used in the ggplotly function.
bats.time<-bats.time%>%
filter(year>2017, year<2022)
ggplot(data=bats.time,
aes(x=monthN,
y=rel_freq,
color=AUTO.ID) )+
geom_line()+
facet_wrap(~year)+
labs(title = 'Number of Total Calls Per Species',
subtitle = "From 2017-2021",
x = 'Year', y = 'Number of Calls')+
scale_x_continuous(breaks = 1:12)
longterm_graph <- ggplot(data=bats.time,
aes(x=monthN,
y=rel_freq,
color=AUTO.ID) )+
geom_line()+
labs(title = 'Number of Total Calls Per Species',
subtitle = "From 2017-2021",
x = 'Year', y = 'Number of Calls')
# using hovertemplate allows us to zoom into the graph
ggplotly(longterm_graph, hovertemplate = paste())